Use of a Self-Learning Neuro-Fuzzy System for
Syllabic Labeling of Continuous Speech

doi:10.1109/FUZZY.1995.409915

淡江大學機構典藏 > 工學院 > 電機工程學系暨研究所 > 會議論文 > Item 987654321/38955

請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/38955

題名:	Use of a Self-Learning Neuro-Fuzzy System for Syllabic Labeling of Continuous Speech
作者:	Hsieh, Ching-tang;Su, Mu-chun;Chienn, Shih-chieh
貢獻者:	淡江大學電機工程學系
日期:	1995-03-20
上傳時間:	2010-04-15 11:00:41 (UTC+8)
出版者:	N.Y.: Institute of Electrical and Electronic Engineers (IEEE)
摘要:	For reducing the requirement of large memory and minimizing computation complexity in a large-vocabulary continuous speech recognition system, speech segmentation plays an important role. In this paper, the authors formulate the speech segmentation as a two-phase problem. Phase 1 (frame labelling) involves labeling frames of speech data. Frames are classified into three types: (1) silence; (2) consonants; and (3) vowels according to two segmentation features. In phase 2 (syllabic unit segmentation) the authors apply the concept of transition states to segment continuous speech data into syllabic units based on the labeled frames. The novel class of hyperrectangular composite neural networks (HRCNs) is used to cluster frames. The HRCNNs integrate the rule-based approach and neural network paradigms, therefore, this special hybrid system may neutralize the disadvantages of each alternative. The parameters in the trained HRCNNs are utilized to extract both crisp and fuzzy classification rules. Four speakers' continuous reading-rate Mandarin speech are given to illustrate the proposed two-phase speech segmentation model. In the authors' experiments, the performance of the HRCNNs is better than the “distributed fuzzy rule” approach based on the comparisons of the number of rules and the correct recognition rate
關聯:	Fuzzy Systems, 1995. International Joint Conference of the Fourth IEEE International Conference on Fuzzy Systems and The Second International Fuzzy Engineering Symposium., Proceedings of 1995 IEEE Int (Volume:4 ), pp.1727-1734
DOI:	10.1109/FUZZY.1995.409915
顯示於類別:	[電機工程學系暨研究所] 會議論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
index.html		0Kb	HTML	370	檢視/開啟
Use of a self-learning neuro-fuzzy system for syllabic labeling of continuous speech.pdf		494Kb	Adobe PDF	339	檢視/開啟

在機構典藏中所有的資料項目都受到原著作權保護.

TAIR相關文章

資料載入中.....